chatgpt-md-converter 0.4.0b1__py3-none-any.whl → 0.4.0b3__py3-none-any.whl

chatgpt_md_converter/telegram_entities/extractors/links.py

@@ -10,7 +10,10 @@ from ..entity import EntityType, TelegramEntity
 _LINK_PATTERN = re.compile(r"!?\[((?:[^\[\]]|\[.*?\])*)\]\(([^)]+)\)")
 
 
-def extract_link_entities(text: str) -> Tuple[str, List[TelegramEntity]]:
+def extract_link_entities(
+    text: str,
+    existing_entities: List[TelegramEntity] | None = None,
+) -> Tuple[str, List[TelegramEntity], List[TelegramEntity]]:
     """
     Extract Markdown links and return plain text with TEXT_LINK entities.
 
@@ -19,14 +22,18 @@ def extract_link_entities(text: str) -> Tuple[str, List[TelegramEntity]]:
 
     Args:
         text: Input text with Markdown links
+        existing_entities: Optional list of entities to adjust offsets for
 
     Returns:
-        Tuple of (text_with_links_replaced, list_of_entities)
+        Tuple of (text_with_links_replaced, link_entities, adjusted_existing_entities)
     """
     entities: List[TelegramEntity] = []
     result_parts: List[str] = []
     last_end = 0
 
+    # Track adjustments: list of (position_in_original, chars_removed)
+    adjustments: List[Tuple[int, int]] = []
+
     for match in _LINK_PATTERN.finditer(text):
         # Add text before this link
         result_parts.append(text[last_end : match.start()])
@@ -38,6 +45,12 @@ def extract_link_entities(text: str) -> Tuple[str, List[TelegramEntity]]:
         link_text = match.group(1)
         url = match.group(2)
 
+        # Calculate how many chars are removed
+        # Original: [text](url) or ![text](url)
+        # New: text
+        chars_removed = len(match.group(0)) - len(link_text)
+        adjustments.append((match.start(), chars_removed))
+
         # Add the link text (without the markdown syntax)
         result_parts.append(link_text)
 
@@ -56,4 +69,23 @@ def extract_link_entities(text: str) -> Tuple[str, List[TelegramEntity]]:
     # Add remaining text
     result_parts.append(text[last_end:])
 
-    return "".join(result_parts), entities
+    # Adjust existing entities
+    adjusted_existing: List[TelegramEntity] = []
+    if existing_entities:
+        for e in existing_entities:
+            new_offset = e.offset
+            # Apply all adjustments that occur before this entity
+            for adj_pos, chars_removed in adjustments:
+                if adj_pos < e.offset:
+                    new_offset -= chars_removed
+            adjusted_existing.append(
+                TelegramEntity(
+                    type=e.type,
+                    offset=new_offset,
+                    length=e.length,
+                    url=e.url,
+                    language=e.language,
+                )
+            )
+
+    return "".join(result_parts), entities, adjusted_existing

chatgpt_md_converter/telegram_entities/parser.py

@@ -167,8 +167,8 @@ def parse_entities(text: str) -> Tuple[str, List[TelegramEntity]]:
     text, inline_entities = extract_inline_formatting_entities(text)
     all_entities.extend(inline_entities)
 
-    # Extract links AFTER inline formatting so offsets are correct
-    text, link_entities = extract_link_entities(text)
+    # Extract links AFTER inline formatting, adjusting existing entity offsets
+    text, link_entities, all_entities = extract_link_entities(text, all_entities)
     all_entities.extend(link_entities)
 
     # Phase 4: Restore code placeholders and create entities

chatgpt_md_converter/telegram_markdown/renderer.py

@@ -34,6 +34,12 @@ def telegram_format(text: str) -> str:
 
     output = re.sub(r"【[^】]+】", "", output)
 
+    # Handle Telegram custom emoji before generic links
+    # ![emoji](tg://emoji?id=123) -> <tg-emoji emoji-id="123">emoji</tg-emoji>
+    emoji_pattern = r"!\[([^\]]*)\]\(tg://emoji\?id=(\d+)\)"
+    output = re.sub(emoji_pattern, r'<tg-emoji emoji-id="\2">\1</tg-emoji>', output)
+
+    # Handle all links including images (! prefix is stripped for non-emoji images)
     link_pattern = r"(?:!?)\[((?:[^\[\]]|\[.*?\])*)\]\(([^)]+)\)"
     output = re.sub(link_pattern, r'<a href="\2">\1</a>', output)
 

{chatgpt_md_converter-0.4.0b1.dist-info → chatgpt_md_converter-0.4.0b3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chatgpt_md_converter
-Version: 0.4.0b1
+Version: 0.4.0b3
 Summary: A package for converting markdown to HTML for chat Telegram bots
 Home-page: https://github.com/botfather-dev/formatter-chatgpt-telegram
 Author: Kostiantyn Kriuchkov

{chatgpt_md_converter-0.4.0b1.dist-info → chatgpt_md_converter-0.4.0b3.dist-info}/RECORD

@@ -9,21 +9,21 @@ chatgpt_md_converter/html_markdown/state.py,sha256=sxbz0ucCakI0KgR86EMZx0nvfU1oi
 chatgpt_md_converter/html_markdown/tree.py,sha256=ryohrhO2X5QepZev3087qPoGmMznqHDwH00TNGoW6a4,2154
 chatgpt_md_converter/telegram_entities/__init__.py,sha256=dopG-8_gWX8xPeD-9dyHdurs5VPrz-wAFFRvHNKiUNg,1855
 chatgpt_md_converter/telegram_entities/entity.py,sha256=oygQxwBsE7AGm2etq6HFZIeo7tBCwsUGniLP17-_Oz0,1705
-chatgpt_md_converter/telegram_entities/parser.py,sha256=P7uQeGaNLLuFa5QLEkkEhdSqaB9xIlUwuZjbXZ8hkGQ,9885
+chatgpt_md_converter/telegram_entities/parser.py,sha256=rNYtWwZuet5_HObrupehnOiNaBoheDusGwOTaX5mQBs,9925
 chatgpt_md_converter/telegram_entities/utf16.py,sha256=eH-yX7d1wZwb3nRdk3kq1LFd-NQMqYHutPbkvX5_DC0,1283
 chatgpt_md_converter/telegram_entities/extractors/__init__.py,sha256=FinTAoRNjuHza0LcEBtpNnBvSR8PFo6cVVDkLg0cV6w,407
 chatgpt_md_converter/telegram_entities/extractors/blockquotes.py,sha256=Di8nG5Oej0hLbBB-WJ3GtlZCvCaa_BNmoUdpFGo9mnY,3596
 chatgpt_md_converter/telegram_entities/extractors/headings.py,sha256=AzjF9jElWfw3d4Qx-81fku7gyTkvb0pKlmow0zUXSk4,1602
 chatgpt_md_converter/telegram_entities/extractors/inline.py,sha256=DYSs7cJEFY3-fGtdMdOA7DO5ERtEF8r2GQns5WcPyto,8745
-chatgpt_md_converter/telegram_entities/extractors/links.py,sha256=fe35PDGKzbF0cRac3HgQ9mVFvYvrtt9LDmS_pL9GPlk,1671
+chatgpt_md_converter/telegram_entities/extractors/links.py,sha256=AmCS8mx7ObY2aL5q7owULemjx-Ivuto_4PtKsL7K45Q,2898
 chatgpt_md_converter/telegram_markdown/__init__.py,sha256=C0Oexz9brpdE-TqEpiAUV78TsZdSrnnH_5yYpEJ03Us,131
 chatgpt_md_converter/telegram_markdown/code_blocks.py,sha256=VPkSisvb6DiS5KAcq0OaX4sqR1YX4VgZvJEXZeAjIWk,3067
 chatgpt_md_converter/telegram_markdown/inline.py,sha256=MPzj5VpDqrlvPy69CCwUIOsWgtgIFfbB4CliV5Wz-TY,2207
 chatgpt_md_converter/telegram_markdown/postprocess.py,sha256=jUf01tAIqHQ1NxNlVGsvU-Yw8SDOHtMoS7MUzaQLf_8,775
 chatgpt_md_converter/telegram_markdown/preprocess.py,sha256=k9XBtwgXkh07SlsqbdcZHwOMHhUGOjiIbOehO5wBnu0,1561
-chatgpt_md_converter/telegram_markdown/renderer.py,sha256=39ZehJq6PVWm-sigeBz7vCycwzEmV4Mwiw36jkGIgXI,1960
-chatgpt_md_converter-0.4.0b1.dist-info/licenses/LICENSE,sha256=SDr2jeP-s2g4vf17-jdLXrrqA4_mU7L_RtSJlv4Y2mk,1077
-chatgpt_md_converter-0.4.0b1.dist-info/METADATA,sha256=9wvQrKaXzPu-_VKWRW_cK4vmbaZkwgtzMrbENVHLZb4,6606
-chatgpt_md_converter-0.4.0b1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-chatgpt_md_converter-0.4.0b1.dist-info/top_level.txt,sha256=T2o7csVtZgr-Pwm83aSUkZn0humJmDFNqW38tRSsNqw,21
-chatgpt_md_converter-0.4.0b1.dist-info/RECORD,,
+chatgpt_md_converter/telegram_markdown/renderer.py,sha256=XQI15mkJe0wSxhuvRl_Md56wX7PsjtmyD8vUFw6RoCA,2326
+chatgpt_md_converter-0.4.0b3.dist-info/licenses/LICENSE,sha256=SDr2jeP-s2g4vf17-jdLXrrqA4_mU7L_RtSJlv4Y2mk,1077
+chatgpt_md_converter-0.4.0b3.dist-info/METADATA,sha256=fj0d7XDaFrmttdJag0-cGWv9ulLK22JRMhOx0fpmWHk,6606
+chatgpt_md_converter-0.4.0b3.dist-info/WHEEL,sha256=qELbo2s1Yzl39ZmrAibXA2jjPLUYfnVhUNTlyF1rq0Y,92
+chatgpt_md_converter-0.4.0b3.dist-info/top_level.txt,sha256=T2o7csVtZgr-Pwm83aSUkZn0humJmDFNqW38tRSsNqw,21
+chatgpt_md_converter-0.4.0b3.dist-info/RECORD,,

{chatgpt_md_converter-0.4.0b1.dist-info → chatgpt_md_converter-0.4.0b3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.1)
 Root-Is-Purelib: true
 Tag: py3-none-any